© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24214
    Prev
    Next
    INDEX
    Explanations

    words starting with re

    np_acts-logits-general · gemini-2.5-flash-lite

    rephrase, redefine, rebrand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     участие
    0.48
    も
    0.47
     đo
    0.45
    শু
    0.45
     ít
    0.44
     жесто
    0.42
     coexistence
    0.42
     extracurricular
    0.42
    ):(
    0.41
     வீ
    0.41
    POSITIVE LOGITS
     re
    0.88
     Re
    0.66
    ing
    0.57
    ification
    0.56
     redefining
    0.52
    Re
    0.52
     reintroduced
    0.50
    再
    0.50
    重新
    0.49
    ifications
    0.49
    Activations Density 0.027%

    No Known Activations